Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1327 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9314. Min Act: -0.0001

Data Index: 1465744 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9274. Min Act: -0.0001

Data Index: 1566095 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9556. Min Act: -0.0001

Data Index: 1446699 (Python Code)

Max Activating Token Index: 441

Text #3

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9014. Min Act: -0.0001

Data Index: 1392191 (Python Code)

Max Activating Token Index: 574

Text #4

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9060. Min Act: -0.0001

Data Index: 1644265 (Python Code)

Max Activating Token Index: 874

Text #5

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9077. Min Act: -0.0001

Data Index: 1522114 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8691. Min Act: -0.0001

Data Index: 1529683 (Python Code)

Max Activating Token Index: 949

Text #7

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8627. Min Act: -0.0001

Data Index: 1508792 (Python Code)

Max Activating Token Index: 802

Text #8

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8864. Min Act: -0.0001

Data Index: 1382451 (Python Code)

Max Activating Token Index: 480

Text #9

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8850. Min Act: -0.0001

Data Index: 1445578 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9101. Min Act: -0.0001

Data Index: 1496041 (Python Code)

Max Activating Token Index: 786

Text #11

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8486. Min Act: -0.0001

Data Index: 1559102 (Python Code)

Max Activating Token Index: 726

Text #12

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8726. Min Act: -0.0001

Data Index: 1402818 (Python Code)

Max Activating Token Index: 407

Text #13

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8685. Min Act: -0.0001

Data Index: 1630604 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8271. Min Act: -0.0001

Data Index: 1422816 (Python Code)

Max Activating Token Index: 278

Text #15

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8253. Min Act: -0.0001

Data Index: 1441447 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8514. Min Act: -0.0001

Data Index: 1417423 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8514. Min Act: -0.0001

Data Index: 1508516 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8177. Min Act: -0.0001

Data Index: 1398036 (Python Code)

Max Activating Token Index: 412

Text #19

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8444. Min Act: -0.0001

Data Index: 1610605 (Python Code)

Max Activating Token Index: 290